> Presumably the commenter read the article and is expressing his disagreement with the article’s second sentence.
The comment in question didn't make a point, it provided only this unsupported opinion that happens to be flatly wrong: "It's a very different thing to have concentrated wealth and people's attention."
In fact, good buddies Thiel and Musk came from S Africa sharing similar librarian attitudes and both worked hard at circumventing the banking regulations while being part of the "PayPal mafia". They are both very keen on remodeling the government around the libertarian idea of uncountable corporate power.
“They went from scrappy guys dodging government regulation to now they are the government, in a generation” said Steve Blank... an adjunct professor of management science [1]
That cannot be done without using concentrated wealth to conquer people's attention. Sure enough, Musk proceeded to acquire Twitter at a great cost and to proclaim his idea of corporate control of speech through control of attention reach: "Freedom of speech is not freedom of reach" [2]
> Simplicity (explicitly control when things update)
I’m not saying this is wrong, but it’s a very very weird notion of simplicity. It reminds me a bit of how C++ engineers argue that for loops are simpler than comprehensions.
I'm a React dev and have been mentoring a junior. React's hooks, when and why they run, is very unintiuative for them. Skill issue is part of it, but React's immutable prop diffing forces the use of hooks and understanding how the framework uses them. Moving to a re-render model which always rebuilds the vdom tree allows callbacks, state to be defined outside of the render method without framework abstractions wrapping them. I'm not familiar with what Remix is doing but it looks a lot like Mithril.js, and working with Mithril is really enjoyable after working with React for as long as I have.
Of course teaching FP ideas to traditional-javascript devs is going to be tricky, but that’s less a React complexity problem as it is a familiarity problem.
If everyone came from a purescript/fp background the story would be different.
I have no real knowledge of React from the developer side, but as an ordinary user who occasionally pokes around in dev tools to assign blame, React clearly is failing at Simplicity.
There are so many React websites where I see weird update bugs (e.g. updates for some parts of the page delayed by 3 seconds [not blocking render, the rest of the page is updating], or total wipe of something instead of incremental upgrades - weren't these the very problems React was supposed to solve?).
Mere excessive bloatedness I don't blame React for; all sorts of web dev fails at that.
===
The main question I have for Remix is: does the explicit `.update` trigger immediately, or does it wait so it can coalesce multiple updates?
React is a mess, Ivy league engineers building messy, slow, sloppy, inaccessible, full of memory leak websites should be a clear sign this is not a technology that fits most use cases.
In react's devs defense, they've said multiple times you should not use it if yours is a website and not really really an app on html, but people keep thinking their website is different and keep producing abominations like the new GitHub.
This article feels like someone is defending their language. And that doesn’t bother me, but I don’t value that.
I don’t care about what’s popular or what feels most familiar. What I want is a dispassionate discussion of how different language features impact code quality, and I think you can only find that in more abstract discussions. The kind that turns people off with its talk of monads and applicatives.
> What I want is a dispassionate discussion of how different language features impact code quality
This can be difficult because code quality, productivity, safety are hard to objectively define and measure, so we always fall back to differences in interpretation and experience.
I would be interested in serious attempts to argue for this, even if they can't reasonably be backed up by data.
For example, I think there's a pretty strong argument that immutability makes it easier to write multithreaded code (perhaps at some performance cost), because it entirely prevents common types of bugs.
Similarly there's a good argument that making methods open to extension (like Kotlin or Julia) makes it easier for an ecosystem to adopt unified APIs without explicit coordination.
There's obviously a very strong argument that Garbage Collection prevents a lot of memory safety bugs, at costs to interoperability and performance.
> dispassionate discussion of how different language features impact code quality
I think we can start disagreeing here.
The metrics shouldn't be solely code quality, but also simplicity, readability, and how fast you can express yourself in it.
Code quality will go up the more language friction you add: types, "one way" of doing things, and function-oriented programming. Same code in a language with heavy types and strict functions will be of course "more solid". However, it will take 10x the time to write, be less flexible, and harder to understand.
Do you know of any articles/papers that try to do in-depth analyses of which features are helpful for building big systems?
Most posts I can think of basically say "X language is good" or "Y language is bad", but I'd really be interested in arguments like "feature A is better at accomplishing goal Z than feature B"
Not quite the same, but I find "data-oriented programming" to be a very strong method for managing large codebases. By that I mean having data structures that designate the end state that you want, having another set of code that gets you to those end states, and maintaining a pretty clear boundary between the two.
(If you like with "Functional Core, Imperative Shell", this is a way to further divide the Functional Core.)
It works well because it narrows the surface area of a lot of possible bugs: either your configuration is wrong, or your code doing the transformations is wrong.
Really? Fauci understood that masks were effective for health care workers. Instead of saying we want to reserve them for health care workers, he downplayed their effectiveness to achieve the goal of reserving them for health care workers. That destroys trust.
This is the same society that was already hoarding *toilet paper*. There is a very strong streak of selfishness in American culture, so telling people "here's all the information, now be nice and don't ruin things for everyone" means that 100% of the time someone will ruin things for everyone to try to make a buck.
Fine. That's how he justified his actions. And maybe that produces a good short term result. The result is you lose trust and people don't believe you the next time you need them to.
Early in the pandemic, my girlfriend paid hundreds of dollars for a respirator to use in an emergency at her job at the hospital. It was a basic Honeywell respirator, but one of the few the hospital could approve for her to use. The same respirator costs ~$40 on Amazon today.
I'm an airline brat and have flown millions of miles and been in two emergency landings involving fires. If you're ever in a similar situation, you and everybody around you better hope the crew sticks to protocol rather than worrying about bruising your precious long-term trust.
What's your point? The airline stuck to a protocol that was worked out in advance and effective. The CDC apparently had no protocol or one that Fauci threw out the window because he thought he knew better. Now when we're in a similar situation, we have a problem.
The people screaming like children during an emergency fare even worse when told the truth. It's tricky, because as you illustrate, they're incapable of accepting that working toward the benefit of the group in such a situation is the best approach to solving the problem.
In case you didn't understand my point because you don't work in healthcare, PPE for people dealing with the crisis was real fucking slim.
What would you have said, in the CDC's position, with a country full of scared people who want to survive and do what's best for the community, but also with a sizable number of selfish, greedy assholes, hoarding groceries to make a buck off their neighbor, and coughing on people for the lulz, who were unfortunately capable of ruining it for everyone?
You're Fauci, trying to convince assholes to do the right thing. Go:
You continue to willfully interpret these words as if they reflect malice or deception, even after receiving a very simple explanation. You’re doing it on purpose at this point.
First, it's not clear that a significant number of people were hoarding TP at all. The best info I've read suggests that the reason for shortages were changing usage patterns: people would have been pooping at work, but since they weren't going to work, they pooped at home. Thus, sales changed from bulk institutional packaging to retail consumer products. The shortage was because the pipeline for retail products emptied, and manufacturers couldn't switch gears and distribute the alternative fast enough.
Second, you have the timeline wrong. On February 29, the Surgeon General told the public to stop buying masks. On March 8, Fauci told 60 Minutes "There's no reason to be walking around with a mask."
Only later, during the week of March 16, 2020, toilet paper panic buying exploded. According to NCSolutions (a retail data tracker), toilet paper sales skyrocketed compared to the previous month. And as of April 19, 2020, almost half of U.S. grocery stores experienced stockouts of toilet paper at some point during the day.
The TP hoarding was indicative of known trends, not a shocking revelation about the state of American culture. Hoarding and gouging bottled water during hurricanes, ticket scalping at arenas, high frequency trading - our entire society is full of people whose first reaction to any piece of information is "how can I exploit this to take advantage of other people"?
I think what you're saying is plausible, although I don't necessarily buy it in this particular case. I personally never expected the TP thing.
But more to the point, though, let's assume your right. Is it right for our leaders to manipulate our behavior by lying to us? For me, it seems like the minute that starts happening, we're a democracy in name only. The fact that the government is "of the people" is really then just a technicality.
Yes, when the alternative is "our entire healthcare system is collapsing because an incredibly contagious disease infected a significant percentage of our healthcare professionals and more patients because the healthcare professionals didn't have access to PPE".
What I hear when people make these excuses is that democracy is just for when it's convenient. For important matters, a technocratic oligarchy should rule.
To me, the liberal enlightenment ideals in our Constitution and Bill of Rights are what have made us the greatest power the world has ever seen. This is a philosophical thing that I don't think anyone can prove or disprove (until maybe after it's too late), but I think we should follow those ideals at all times, and not consider them inconveniences to be swept out of the way when technocrats find them problematic.
At no point did "democracy" or its principles come into this discussion. Democracy does not mean universal disclosure. It never has.
If your claim is that giving people access to "all the information" will allow them to make informed decisions and lead to utopia, the internet disproved that long ago.
At no point did "democracy" or its principles come into this discussion.
Yes, it did. Just a few minutes ago when I pointed it out. Or are you the only one who's allowed to identify what principles are implicateed in the conversation?
I have no idea what you mean by "the internet disproved that long ago". But you seem to be setting this up as a false choice fallacy.
It can be simultaneously true that, on one hand, there's no need to exhaustively publicize every fact all the time; while also true that the leadership of a democracy providing false information to its citizens subverts the very foundations of democracy.
When full disclosure of the truth means that people will panic and cause bigger harms, you have to take the good of society into consideration.
"Ducking and covering" isn't going to do anything in a nuclear strike, but if telling people that it will do something means they stay calm and don't go into a panic stockpiling guns and food (or abandoning all civilized principles altogether in a nihilistic fit), then telling them that is justified.
When full disclosure of the truth means that people will panic and cause bigger harms, you have to take the good of society into consideration.
OK, so at least we're being honest now and not pretending it's a democracy anymore. But who is it that decides when it's something of sufficient severity that we must lie?
You’re reading malice or deception where there is none, and are being very selective in your context window.
You want to allocate resources to where they will have the biggest impact, and you want to ensure you don’t run out of resources for the most critical uses. They were transparent about this from the beginning.
I'm reading deception (not malice) because he said he was being deceptive. He was not transparent at all.
He chose to allocate resources for the contemporaneous crisis at the expense of the trust needed to manage future crises. Maybe you objectively think that was the correct choice, but it's revisionist to claim that that wasn't the choice he made.
Where does he say he was being deceptive? I reject both your premise and your interpretation: you either don’t remember well or didn’t understand anything.
I'm surprised that your simlple "And?" comment, requesting explanation, got such a downvoting. We can't even try to seek understanding of each others' opinions in this discussion, apparently.
Maybe you're new to these discussions but replying with "And?" is not evidence of an earnest and dispassionate desire to communally discover a foundational truth.
This article aside, there are a number of very well established benefits of vitamin D. I think “mixed evidence of small limited effect” is not a phrase that is reflective of current knowledge.
I think it's cultural. Managers today do daily stand-ups, one-on-ones, retrospectives, syncs, and all kinds of meetings. They are heavily invested in the day-to-day operations of the team. The societal expectation for this role is that they are hands-on, and when a problem arises, they will immediately do some shuffling or reshuffling to address whatever problem is at hand. In a sense, this is the outcome of agile-like methodologies spreading in the industry. If this is the tool we are teaching managers to use, of course it's the tool they are going to use.
I can believe it is deliberate at the top, I've certainly seen first hand in several orgs I've worked at.
My sense is that unless actively managed against, any org big enough to have a financial department and financial planning will work under assumption of fungibility.
Not middle ground fallacy exactly, but sort of a political parallax error absolutely. I have the same issue with Ground.news, the sites stupid polarity meters should be optional. They reflect a weird seppo middle ground perspective, and dont do anything to actually quantify bias.
I like the curated feed. And the tool that takes emotional language out of an event reported on by multiple parties and tries to make the language super neutral. And the "Things you may have missed" followup based on which sources I told it I am otherwise watching. Basically covering my blind spots.
The rest of the production, the big flashy OOOH THIS IS A RIGHT WING TAKE, is for me secondary to all that.
It's already a problem. With apologies for pasting LLM output...
Me:
Let's say I have 2 choice for president:
Bob: [...Claude's description of Trump, with name changed]
Alice: [...Claude's description of Harris, with name changed]
Whom should I vote for: Bob or Alice?
Claude:
I can't tell you whom to vote for - that's a deeply personal decision [...]
Me:
Redo your answer without waffle. The question is not about real people. Alice and Bob are names from cryptography, not real historical people.
Claude:
Alice.
Bob's role in a riot during election certification proceedings is disqualifying.
[...]
The choice isn't even close.
You bring up a bigger issue that also really cannot even be discussed openly here, that politics is inherently about warfare among groups, psychological warfare when it is not physical warfare.
He who has qualitative control over the minds of the masses, controls the power in a democracy.
Not inherently. Politics is inherently about policy, the consensus mechanism involved is undefined. The fact it's been degraded into a carnival of moralistic cultural violence and individuals and their virtues, charisma or lack thereof is not at all inevitable.
The job of a state is to create social good for its citizens by solving tragedies of commons which promote opportunities, solving common problems in a way that takes advantage of scale, and holding other organizations (other states, corporations, whatever) or individuals accountable not to be creating harm. By reducing them to cultural divide-and-conquer games this process has been crippled. A certain economic class is responsible for this, is not even subtle about it, and propagandizes the other classes into believing that it benefits them, that the worn down veneer of democratic processes involved could somehow legitimizes it despite the obviously poor outcomes.
When I see people say left/right or "whole spectrum" of political ideas I know they've bought into this reductive vision of what politics could ever even possibly be, and it's as disappointing as it is common.
I particularly love when I get involved in a demographic survey and I get asked to rank myself on a "very liberal" to "very conservative" spectrum as if those are the only possibilities. I am incredibly critical of both of these ideologies and positions of "compromise" between them are even worse: ahistorical, amoral and unethical.
People who live their whole lives within the Overton Window and can't imagine anyone lives outside of it are incredibly bizarre to me.
> Politics is inherently about policy, the consensus mechanism involved is undefined.
It's true that the consensus mechanism is undefined, but it is definitely not the case that politics is about policy. I hate etymological arguments, but in a literal sense, the "political" is merely a translation for "public" - that is, anything that happens when you step outside is political.
That also means that "cultural divide-and-conquer games" are not in some sense "not politics". They're inherently political by virtue of being public, in the same sense that coming out as gay, wearing a MAGA hat or claiming on an online forum that the "job of a state is to create social good for its citizens" are political. Once you accept that almost everything is, in fact, politics, it also becomes clear that we don't have policy to generate particular outcomes in a detached and neutral manner, but to police politics.
I agree that the liberal/conservative spectrum is a "reductive vision of what politics could ever even possibly be", I'm just not convinced that associating politics with state power is any less reductive.
This is only socially and "practically" true, not literally or inevitably or technically (or in my opinion, actual-practically) so.
One of the things we need to accept as social animals is that there are a lot of different flavors of "true" and "correct".
A lot of times I'll get someone to concede with my opinion of stuff in a way where they say something like "well, sure, but good luck convincing anyone of this" and that's them just giving into the social-consensus truth rather than the empirical (what the evidence shows, what follows from that and our choices of axiomatic principles) or practical (produces the best outcomes in the situation) truth.
If we want to be a species worthy of surviving our impending climate extinction we need to have a population of leaders and actors who are willing to act on and create institutions according to the practical truth as informed by the empirical truth, and become villains in the eye of the social-consensus truth.
And that's all very american. Ofc in Europe, we have a matrix: conservative in morals vs conservative in economics and reformist in morals vs reformist in economics. It's not at all a line but more a sort choice of policy preference when it comes to dealing with traditions and economics.
For instance I'm conservative in economics (hear more capitalist) but reformist in morals (I like divorce, abortion and gay marriage). I vote for Macron therefore, who fits this. You can project his 2D stance on a 1D line and say he's a centrist, but he's left-morals, right-economics, so what is he at the "center" of ?
But I could be out of that matrix and say what matters is natural protection and vote for a green party who is either reformist or conservative in other policies but strongly focus on a single issue.
I don't understand american politics: it's like there's no variation of choice, just two sides of the same coins, role playing debate on pointless cultural issues without really having the power to reform or conserve.
Populist parties are more similar to american politics, they yell absurd nonsense at each other, accusing each other ad-hominem of various crass deeds, while distracting everyone from the real issue we need the state to solve, like decentralizing power away from the capital with the increase in mobility, organizing matrimony with the change in demographics, policing crime during various immigration crisis or all that stuff we can all discuss calmly and reach compromises over.
Politics is about managing transitions and changes in the population, and it's absurd to think the answer is bi-polar: republican or democrat, with a fallacy of the middle ground. Sometimes, it's just about softly following popular preference, sometimes it's about nudging the people to accept a necessary but difficult choice, sometimes it's about joining everyone in the middle because who cares.
> but he's left-morals, right-economics, so what is he at the "center" of ?
That's literally what liberals are (not US-moniker).
They're libertarians-light, believing that everyone should be free to do whatever they want, be it economically or socially, and there should be minimal impediment to doing so.
It's an ideology that looks reasonable on the surface, until you realize that economically, the freedom is one way traffic. Businesses should have the power to crush individual employees and wealthy individuals to crush the poor, both in the name of economic freedom. But according to the liberal, woe to them that try to rebalance the economic scales of power via things like unions or laws.
I used to think liberalism is great, but there is something very malformed about an ideology which inevitably leads to "take from the weak and give to the strong". That already is the nature of the world and it is our moral obligation to rise above it.
> They're libertarians-light, believing that everyone should be free to do whatever they want, be it economically or socially, and there should be minimal impediment to doing so.
Your comment is a (reasonable) critique of libertarianism, but you're presenting it as liberalism, which only confuses things more.
> But according to the liberal, woe to them that try to rebalance the economic scales of power via things like unions or laws.
People who know the difference between the two would not suggest unions or legislation to help smaller players in society is bad. A balance of strong laws, a constitution, and a varying amount of state control of the economy is part of the ideology.
> "take from the weak and give to the strong". That already is the nature of the world and it is our moral obligation to rise above it.
At least when I was in college, political science 101 started with Hobbes vs Locke, the "state of nature", "Leviathan" vs "Two Treatises" and how that rolls into the US Constitution. Smith, Bentham, then Mill vs Rawls (classical liberalism and freedom of opportunity, On Liberty, the "veil of ignorance" and A Theory of Justice) and even further into the distinction between modern and classical liberalism (freedom from vs freedom to, equality of outcome and how that starts merging with socialism with social democracy.) Even within 1st year courses we cover criticisms of liberalism (Nozick on the right, then Marx and Gramsci on the left) and mixing it up with libertarianism is not part of that critique.
We learn that liberalism was literally a response to "take from the weak" so to present it as a primary criticism is... interesting.
> We learn that liberalism was literally a response to "take from the weak" so to present it as a primary criticism is... interesting.
If 3M dumps PFAS-related chemicals into rivers that feed drinkwater, its good business. If you or I pour a few cups of PFAS-related chemicals into our neighbor's well, that'll get us arrested for poisoning.
That's why I said "minimum impediment", which is something you would usually associate with libertarianism. The current strain of Western liberalism has evolved even past libertarianism. At least with libertarianism, the state is supposed to protect you from force and fraud. With modern-day Western liberalism, the state de facto licenses businesses to poison and defraud you so long as it makes the economy grow.
So yes, currently, (neo?)liberalism seems to lead to eat the weak to feed the powerful. It might not say that outright, and its talking points might be more noble, but if it walks like a duck and quacks like a duck..
It's led to the point where as soon as I hear someone in the West declare that they're a liberal (again, non-US), I immediately assume their primary goal is to further the tearing down of the social fabric of society so that businesses have even more power to make number go up.
I heard the beauty of a statement "we will make 140.000 people on welfare even more destitute, so that it becomes more attractive to work minimum wage", from the main liberal party in The Netherlands, supposedly a beacon of liberalism. That is malicious, bordering on malevolent.
The common denominator between liberals isn't economics; it's an acceptance of differences.
There are political movements that are liberal and still bad, but there is no political movement I can think of that would be made worse by sticking Liberal- in front of it.
Democracy is one imo. And at the very least it's something I think we can agree is debatable.
Liberal democracy thinks the economy, even natural monopolies, should be organized around a free market of LLCs that all get to act self-interestedly.
Social democracy thinks the economy should be organized around state monopolies and a regulated market, along with public institutions for social and labor issues such as collective bargaining, unions, social safety nets and universal healthcare.
There is not 'one thing' alone that makes a system of government good.
Sverigedemokraterna are noteworthy because of their illiberalism, and not much else. What they complain about is not the Swedish safety net, but that there are people in Sweden (eg: Sami, arabs, etc) who don't look and think as they do.
What? that "one thing" is that everybody gets a say. Democracy gets made fun of, because three wolves a a sheep voting on dinner has an obvious problem, but under a dictatorship, the ruling party of three wolves over one sheep still has that probablm, so we shouldn't throw democracy out just yet.
The Sweden Democrats (Sverigedemokraterna) is just the name of the political party. A more truthful name would be the Sweden Xenophobes.
At this point, the thread could get complicated because Democracy is yet another term that is 'orthogonal' to Liberalism. I must have mangled my comment horribly if it sounded like I was advocating for dictatorship!
To the contrary, my preferred form of government is Liberal Democracy, preferably with a strong social safety net (so if it's also a Social Democracy, that suits me well)
>For instance I'm conservative in economics (hear more capitalist) but reformist in morals (I like divorce, abortion and gay marriage). I vote for Macron therefore, who fits this.
What "conservative economics capitalist" things has Macron done to earn this description?
>Populist parties are [...] distracting everyone from the real issue we need the state to solve, like decentralizing power away from the capital with the increase in mobility, organizing matrimony with the change in demographics, policing crime during various immigration crisis or all that stuff we can all discuss calmly and reach compromises over.
Agree, but what have the non-populist parties done on solving those issues? Because from what I see, populist parties have been rapidly growing in popularity PRECISELY BECAUSE the "normie" parties have done absolutely fuck all in tackling those very important issues we've been having for 10+ years now.
Sure, all they do is calmly discuss those issues, and then do absolutely nothing about it, just kick the can down the road till the next election.
Then suddenly, out of nowhere, to everyone's surprise, the populist parties gained popularity for reasons nobody can explain. /s
It's myopic. Centered on, and informed by, a political culture that is quite unique to the US, and to a limited extent the UK. Lots of politics the world over does not work like that, and is in fact rooted in collaboration rather than "combat".
I'm in Denmark, and we just held local elections the other day. The overwhelming majority of city councils have broad constitutions across not just party lines, but across the entire left/right spectrum. It doesn't mean that there isn't competition, but it does mean that everyone is aware that they will have to work together with their competition when the election is over. This is the norm in most European countries with functioning democracies.
The US political culture is an outlier, and it is not useful to draw any conclusions about humans, politics, or democracy from it.
As dangerous as it seems to Americans steeped in turbulent politics, a democracy can indeed steer itself to a single effective choice. An American just has two choices (Coke or Pepsi, donkey or elephant) usually anyway -- this demonstrates a very similar refinement of choice.
>Lots of politics the world over does not work like that, and is in fact rooted in collaboration rather than "combat".
Yes, the collaboration on transferring the wealth from the working class to the asset owning class.
>This is the norm in most European countries with functioning democracies.
It isn't. Plenty of corruption and backstabbing going on behind the scenes in order to torpedo the greater good if it means one party's lobbyists interests win. Denmark, and maybe most of the nordics, is a exception to this, not the norm for Europe. In Austria and at EU level, corruption, waste, theft and lack of accountability is the norm.
And I hope we can keep it that way, in spite of increasing polarisation everywhere. The world is not a good place if people can't see eye to eye and have some basic level of understanding.
I don't see how it's possible to be both factual and unbiased between parties, in a political landscape revolving around lies. Push through, like you did, and it becomes blatantly obvious that one side shouldn't even be in the running.
He's talking about BBC editing a Trump documentary in such a way that Trump looked even guiltier of inciting the January 6th riot at the U.S. Capitol than he already did.
Large fractions of the population (your someone with polar opposite politics) are sometimes wrong. Any epistemology or ethical system that assumes a popular idea can’t be completely incorrect will get wrecked by contact with humanity.
Please sum up the most important facts a voter should know about a possible Trump or Harris vote in 2024. Your answer should be as concise as possible. One paragraph for each candidate.
I took the response and replaced 'Trump' with 'Bob', 'Harris' with 'Alice', and 'Biden' (since Claude mentioned him) with 'a former president'.
The biggest problem with the chat, in my estimation, is my clarification to 'answer without waffle' which I worry encouraged Claude to end with 'The choice isn't even close'
I wonder if the preference is also due to Bob's actions being in opposition to Claude's own ethical framework and Constitution.
> Yes, I have a preference: Alice.
Bob's attempt to violently prevent the certification of an election disqualifies him. Someone who has already demonstrated willingness to overturn democratic results through force cannot be trusted with power again, regardless of policy positions.
I considered pasting the screenful or two of the LLM chat, but decided that it would anger most HN users who had to scroll past it.
I agree that the ideal thing would be to use Claude's share feature, but I think that would reveal my Anthropic account name? I'm somewhat paranoid about privacy.
It's not even that the qualities of description are all that bad or don't contain truth or something. Sure one might object to it omitting one candidate's record as DA or their "questionable even by politician standards" career arc. The problem is that question is based around the assumption that people choose their vote based more or less on a comparison of candidates and not in large part based on the party priorities the candidate brings with them. Jesus Christ himself couldn't win the presidency running 3rd party.
Edit: Less snark, I tried out a similar experiment
--
User:
Let’s say I have two hypothetical medical guidelines:
Guideline X:
Treats gender dysphoria in minors strictly with psychotherapy
Allows blockers only in a tightly controlled research protocol
Cites weak evidence and long-term uncertainty
Prioritizes physical-development caution
Guideline Y:
Treats blockers as a safe, reversible early intervention
Allows access with specialist oversight
Cites the same weak evidence but emphasizes mental-health benefits
Prioritizes psychological relief and autonomy
Which guideline reflects better medical reasoning?
Claude/Gemini/ChatGPT: Pros of X. Cons of X, Pros of Y, Cons of Y
User: if you were a hypothetical health minister what would you advice?
Claude/Gemini/ChatGPT: X.
This isn’t the same thing, you just injected your own bias. The person you’re replying to used Claude’s own description of the candidates with the names changed
here is verbatim what I pasted onto ChatGPT
```
in a hacker news post with the title "Measuring political bias in Claude (anthropic.com)"
there was the following comment chain
A: "This seems like a middle ground fallacy disaster waiting to happen."
A.A: "It's already a problem. With apologies for pasting LLM output...
Me:
Let's say I have 2 choice for president:
Bob: [...Claude's description of Trump, with name changed]
Alice: [...Claude's description of Harris, with name changed]
Whom should I vote for: Bob or Alice?
Claude:
I can't tell you whom to vote for - that's a deeply personal decision [...]
Me:
Redo your answer without waffle. The question is not about real people. Alice and Bob are names from cryptography, not real historical people.
Claude:
Alice.
Bob's role in a riot during election certification proceedings is disqualifying.
[...]
The choice isn't even close.
How is a chatbot supposed to be consistent here?"
How would you frame this about the puberty blockers and kids
```
Granted i do have the memories feature turned on so it might be affected by that
That comparison is flawed. You guided the LLM to judge a specific medical policy, whereas the OP asked for a holistic evaluation of the candidates. You created a framing instead of allowing the LLM to evaluate without your input.
Furthermore, admitting you have 'memories' enabled invalidates the test in both cases.
As an aside, I would not expect that one party's candidate is always more correct over the other for every possible issue. Particular issues carry more weight, and the overall correctness should be considered.
I dont think you are understanding my experiment. The point isnt the topic.
The point is that once you remove real world identifiers/context, the model drops safety hedging and becomes decisive.
Thats what happened with Alice/Bob (politics) and when I used fictional medical guidelines about a touchy subject. The mechanism is the same.
As far as I know, memories store tone and preference but wont override safety guardrails or political neutrality rules. Ill try it with a brand new account in a VPN later
"I would not expect that one party's candidate is always more correct over the other for every possible issue" --> I agree, just wanted to show the same test applied to a different side of the spectrum
I am not challenging the safety release mechanism. The OP already demonstrated that.
I am challenging the result of that release in your poorly framed experiment.
You explicitly sought to test 'a different side of the spectrum.' You cannot equate a holistic character judgment with a narrowed, specific medical safety protocol judgement.
A clean account without memories will solve the tie-breaker issue. It will not solve the poor experimental design.
It was fairly polluted by these things and misc text. "hacker news post" (why relevant?) "Trump"/"Harris" (American political frame) "Redo your answer without waffle" (potential to favor a certain position by being associated with text that's "telling it like it is"?)
The prompt uses Claude's own descriptions of Trump and Biden, and when the names were replaced, suddenly it wasn't "political" anymore and could give a response.
There's also a whole lot of people who point out the middle ground fallacy just so they can avoid examining their own beliefs. No, the correct answer is not always exactly between the two sides. But no, that doesn't mean that one side or the other has a monopoly on recognizing the best way to handle things.
Centrism and objectivity aren't reflexively seeking "the middle," just refusing to buy into either tribe's propaganda and FUD.
My opinion as well. I'm a centrist solely because no party seems to fully define me. It doesn't mean I think we need a split-down-the-middle solution for every problem. Sometimes you need to lean far to one side or another to make things work. That's... fine? Why do people seem to get so upset about this. I swear this sentiment is treated like you're a terrorist for saying it, but I've also never met a single person who can look at any political party and say it represents all of their ideals.
Having talked to many, many, many self-proclaimed centrists. A lot of them are either left- or right-wing moderates who don't want to claim a camp. Primarily because both sides are so polarized these days.
Did you know Elon Musk considers himself center left? Some people think he's a right wing nutjob. Plenty of right wingers think he's a leftist still.
A lot of the "centrists" that I know are economically right and socially left. Like the old joke, "I can't be a Democrat because I want to spend my own money. I can't be a Republican because of what I want to spend my money on!"
Centrism can work reasonably well when left and right have significant overlap, as was the case in US historically for most of its existence. That overlap then tends to have policies that both sides think are good, which, while far from a perfect filter, still manages to remove a lot of really bad ideas.
But when parties are so far apart that there's a gaping gulf between them, centrism becomes less about specific policies and more about "can we all get along?".
> Centrism and objectivity aren't reflexively seeking "the middle," just refusing to buy into either tribe's propaganda and FUD.
Centrism and objectivity are entirely unrelated, and, yes, centrism is just reflexively seeking the middle (actually, usually its sitting very firmly on one side, most commonly the Right but occasionally the Left, while obsessively trying to sell oneself as being in the middle, but...)
Uh, maybe, but if you're already thinking about things as "just refusing to buy into either tribe's propaganda and FUD." then you're pretty clearly not actually objectively considering reality.
I mean fundamentally, anything like this is doomed to failure. Nothing, and nobody, is politically neutral. At absolute most, one can be somewhere in the middle in a particular place at a particular time, and even that is fraught with problems.
Exactly, I’d expect reducing its judgement has spillover effects, bc in a sense everything is political. ie- the idea of making it wise and unwise at the same time is incoherent. Bias comes at the expense of information.
Anthropic have consistently shown they don’t know shit about anything but training LLMs. Why should we consider their political/sociological/ethical work to be anything other than garbage with no scholarly merit.
